Learning Embeddings for Product Size Recommendations

Despite significant recent growth in online fashion retail, choosing product sizes remains a major problem for customers. We tackle the problem of size recommendation in fashion e-commerce with the goal of improving customer experience and reducing financial and environmental costs from returned items. We propose a novel size recommendation system that learns a latent space for product sizes using only past purchases and brand information. Key to the success of our model is the application of transfer learning from a brand to a product level. We develop a neural collaborative filtering model that is applicable to every product, without requiring specific customer or product measurements or explicit customer feedback on the purchased sizes, which are not available for most customers or products. Offline experiments using data from a major retailer show improvements of between 4-40 % over the matrix factorisation baseline.

[1]  Rajeev Rastogi,et al.  Bayesian Models for Product Size Recommendations , 2018, WWW.

[2]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[3]  Alejandro Bellogín,et al.  Time feature selection for identifying active household members , 2012, CIKM '12.

[4]  B. Lindsay Mixture models : theory, geometry, and applications , 1995 .

[5]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[6]  Mengting Wan,et al.  Decomposing fit semantics for product size recommendation in metric spaces , 2018, RecSys.

[7]  P. Rousseeuw Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[8]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[9]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[10]  Abdul-Saboor Sheikh,et al.  A hierarchical bayesian model for size recommendation in fashion , 2018, RecSys.

[11]  G. Mohammed Abdulla,et al.  Size Recommendation System for Fashion E-commerce , 2017 .

[12]  Ângelo Cardoso,et al.  Product Characterisation towards Personalisation: Learning Attributes from Unstructured Data to Recommend Fashion Products , 2018, KDD.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Rajeev Rastogi,et al.  Recommending Product Sizes to Customers , 2017, RecSys.

[15]  CARLOS A. GOMEZ-URIBE,et al.  The Netflix Recommender System , 2015, ACM Trans. Manag. Inf. Syst..